Nvidia RTX 40 Series Could Have Incredible TFLOP Performance

Nvidia’s upcoming GeForce RTX 40-series GPUs could potentially double the 3090 Ti’s teraflops (TFLOPS), and even more than 100 TFLOPS.

Reliable tipster Greymon55, who has spread several rumors about Nvidia’s next-gen graphics cards, has confirmed his stance on the graphics compute performance (FP32) of Lovelace video cards.

If lovelace goes to 2.5GHz you get about 90 tons of FP32 and 3090ti is only 40 tons.😬

— Greymon55 (@greymon55) January 25, 2022

He tweeted that “if Lovelace gets to 2.5GHz, you’ll get about 90 tons of FP32.” Previously he had referred to the possibility of the GeForce RTX 40 series with between 85 and 92 TFLOPS in FP32 in November 2021. For reference, Lovelace is believed to be Nvidia’s codename for its next-generation GPUs.

As indicated by NotebookCheck, TFLOPS (tera (trillion) floating operations per second) has become an increasingly common measure of how powerful a graphics card is in general. Unlike gigahertz (GHz), which determines a processor’s clock speed, TFLOP measures a computer’s performance.

Nvidia’s Ampere architecture allowed the RTX 3090 to be powered by 35.58 TFLOPS in FP32 (single-precision floating-point format), while the highly anticipated GeForce RTX 3090 Ti GPU would deliver 40 TFLOPS.

An RTX 4090 graphics card (based on the AD102 GPU) offering 90 TFLOPS would therefore be 2.5 times the teraflop count of the RTX 3090. NotebookCheck shows how an upgraded RTX 4090 Ti based on the next-gen Lovelace microarchitecture could theoretically exceed 100 TFLOPS. In comparison, the PlayStation 5 and Xbox Series X have 10.28 TFLOPS and 12.15 TFLOPS, respectively.

With such a high TFLOPS count, it bolsters an earlier rumor that the RTX 4090 or RTX 4090 Ti might require a massive 1200 watt power supply unit (PSU).

Greymon55 also pointed out that Lovelace video cards would offer “double the performance” of the GeForce RTX 3090. Considering the rumored tech specs, that statement could very well become reality – in addition to 18,432 CUDA cores, the RTX 4090 could sport 24 GB of GDDR6X memory, complemented by a clock speed between 2.3 GHz to 2.5 GHz. GHz. Greymon55’s sources indicate that the next-gen Nvidia GPUs will arrive in September 2022.

So far I know that the next generation GPU has not suffered any delay, in fact it is not far, just more than half a year isn’t it?😁

— Greymon55 (@greymon55) January 19, 2022

As for the GeForce RTX 3090 Ti, the graphics card is said to be released on January 27, but Nvidia has apparently halted production of the card for now. Anyway, when it eventually launches, it will be the most expensive GPU ever ($4,500). That price record will most likely be broken when its successor, the RTX 4090 Ti, hits the market.

Nvidia is reportedly spending several billion dollars to run TSMC’s 5nm process node required for GeForce RTX 40 GPUs.

Editor’s Recommendations

Leave a Reply

Your email address will not be published. Required fields are marked *